Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Peak performance and energy levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rę
    -0.08
    .Distance
    -0.08
     Needle
    -0.08
     στε
    -0.08
    ankan
    -0.08
    ින
    -0.08
    step
    -0.08
     Families
    -0.07
    _repr
    -0.07
     താമ
    -0.07
    POSITIVE LOGITS
     migliori
    0.10
     mornings
    0.09
     leistungs
    0.08
     meilleures
    0.08
     wasted
    0.08
     evenings
    0.08
     favors
    0.08
     freshest
    0.08
     ling
    0.08
     melhores
    0.08
    Act Density 0.013%

    No Known Activations